LLM EXPLORER 64,442 MODELS INDEXED

Gemma 4 26B A4B It AWQ 4bit by axteam

By axteam · 75 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B It AWQ 4bit is an open-source language model by axteam. Features: 26b LLM, VRAM: 17.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.43, ELO: 1438.

  4bit   Awq Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Compressed-tensors   Conversational   Endpoints compatible   Gemma   Gemma4   Image-text-to-text   Int4   Quantized   Region:us   Safetensors   Vllm
Model Card on HF 🤗: https://huggingface.co/axteam/gemma-4-26B-A4B-it-AWQ-4bit 

Gemma 4 26B A4B It AWQ 4bit Benchmarks

LMSys ELO 1438 vs 1272 (so35) 13.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 4 26B A4B It AWQ 4bit Parameters and Internals

LLM NameGemma 4 26B A4B It AWQ 4bit
Repository 🤗https://huggingface.co/axteam/gemma-4-26B-A4B-it-AWQ-4bit 
Base Model(s)  Gemma 4 26B A4B It   google/gemma-4-26B-A4B-it
Model Size26b
Required VRAM17.6 GB
Updated2026-10-15
Maintaineraxteam
Model Typegemma4
Model Files  17.6 GB
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4B It AWQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 26B A4B It AWQ 4bit0K / 17.3 GB306902391
Gemma 4 26B A4B AWQ 4bit0K / 17.6 GB641
Gemma 4 26B A4B AWQ 8bit0K / 29.2 GB331
Gemma 4 26B A4B It AWQ 8bit0K / 29.2 GB301
...emma 4 26B A4B It Qat AWQ INT40K / 17.2 GB2314318
...x Imatrix3plus AWQ High6 Top400K / 15.5 GB410
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB3369650
Gemma 4 26B A4b It 4bit0K / 15.4 GB2754379
OTel 2.0 Decision 26B A4B 4bit0K / 17.3 GB631
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB34873
Note: green Score (e.g. "73.2") means that the model is better than axteam/gemma-4-26B-A4B-it-AWQ-4bit.